MentionForge

Get a frozen research snapshot

get_example

Read-onlyIdempotent

Return a frozen Cloudflare Workers research snapshot. Omit view or set view=full for the complete fixture; view=compact slices mentions and citations to 8 and clears theme examples; query and filters are ignored because the snapshot is fixed; extra keys besides view are rejected; {} is valid. Use this free fixture when you need a sample payload; for liveness use get_health instead; for list price use get_pricing instead; for live mentions use research_mentions. Never charges, never hits live sources, and does not consume the shared 10-call trial.

Input Schema

Name	Required	Description	Default
`view`	No	Optional snapshot size: full or compact.

Output Schema

Name	Required	Description
`meta`	Yes	Request metadata including billing and freshness
`query`	Yes	Echo of the researched query
`themes`	Yes	Ranked themes extracted from mentions
`voices`	No	Top non-placeholder authors by engagement
`volume`	Yes	Mention counts and trend for the window
`signals`	No	Spike and negative-concentration flags for this window
`summary`	No	Executive summary when include_summary was true
`markdown`	No	Deterministic pasteable brief when include_markdown was true
`mentions`	Yes	Cited mention rows (may be empty — empty windows still succeed)
`citations`	Yes	Sources used to build the brief
`sentiment`	Yes	Aggregate and per-class sentiment
`timeframe`	Yes	Echo of the requested window
`share_of_voice`	No	Present when the query is a vs / multi-brand compare

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 27, 2026

changedOutput schema / properties / meta / properties / billing / properties / amount_usdc / description

Previous value: -"USDC charged for this call (`0` on trial/sandbox/replay)"New value: +"USDC charged for this call (`0` on trial/sandbox/replay/key plan)"

addedOutput schema / properties / meta / properties / billing / properties / plan

Added value: +{
+  "const": "key",
+  "description": "Present when billed against a Stripe API-key plan",
+  "type": "string"
+}

changedOutput schema / properties / meta / properties / billing / properties / tx_hash / description

Previous value: -"Settlement transaction hash, or null until settle / on trial"New value: +"Settlement transaction hash, or null until settle / on trial / key plan"

Changed1 schema field changedOct 11, 2026

addedOutput schema / properties / meta / properties / sources_disabled

Added value: +{
+  "description": "Requested platform ids skipped because they are in DISABLED_SOURCES",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

Changed2 schema fields changedSep 21, 2026

removedInput schema / description

Removed value: -"No arguments. Free fixture payload."

addedInput schema / properties / view

Added value: +{
+  "description": "Optional snapshot size: full or compact.",
+  "enum": [
+    "full",
+    "compact"
+  ],
+  "type": "string"
+}

AddedSep 21, 2026

TDQS

A4.6/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, closed-world, non-destructive, so the safety bar is low, yet the description still adds real context: never charges, never hits live sources, and does not consume the shared 10-call trial. It also discloses invocation quirks annotations cannot cover — query/filters ignored, extra keys rejected, {} valid. Slightly short of 5 only because it doesn't say anything about the response shape's stability beyond 'frozen'.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose, then the alternative routing, then the cost/safety guarantees. The semicolon-chained middle section is dense but each clause carries distinct information; no sentence is filler, though the run-on style costs a little readability.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values needn't be described. Combined with full param coverage, explicit invocation rules (extra keys rejected, {} valid), and sibling routing, an agent has everything needed to call this correctly on the first attempt.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the enum is already documented, so the baseline is 3. The description earns above baseline by explaining what compact actually does — slicing mentions and citations to 8 and clearing theme examples — which is behavioral meaning the schema enum cannot convey.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a specific verb and resource ('Return a frozen Cloudflare Workers research snapshot') and makes the fixed-fixture nature unmistakable. It is immediately distinguishable from siblings like get_health, get_pricing, and research_mentions, which are named explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives both sides of the decision: 'Use this free fixture when you need a sample payload' plus three named alternatives with the condition that selects each ('for liveness use get_health instead', etc.). Nothing is left to inference about when not to call this.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All MentionForge tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.